Triple

T20784775
Position Surface form Disambiguated ID Type / Status
Subject The Singing Nun E511598 entity
Predicate filmingProcess P2760 FINISHED
Object Panavision NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Panavision | Statement: [The Singing Nun, filmingProcess, Panavision]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Panavision
Context triple: [The Singing Nun, filmingProcess, Panavision]
  • A. Panavision chosen
    Panavision is an American company renowned for designing and manufacturing high-end motion picture cameras and lenses widely used in professional film production.
  • B. VistaVision
    VistaVision is a high-resolution widescreen motion picture format developed by Paramount Pictures in the 1950s that runs 35mm film horizontally to achieve finer image quality.
  • C. CinemaScope
    CinemaScope was a widescreen film format introduced in the 1950s that used anamorphic lenses to create a much wider image than traditional movie presentations.
  • D. Ultra Panavision 70
    Ultra Panavision 70 is a widescreen 70mm motion picture film format known for its extremely wide aspect ratio and high image resolution, used in epic and large-scale cinema productions.
  • E. Steadicam
    Steadicam is a camera stabilization system that allows smooth, fluid tracking shots while the operator moves freely without the shakiness of handheld filming.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0b4cac7a48190a715cb3d545df2b4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c28b4ce88190a45f1c99b58d18eb completed April 21, 2026, 12:19 a.m.
Created at: April 16, 2026, 12:38 p.m.